video-ad-specs

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides links to installation documentation and scripts hosted on GitHub by the inference-sh organization. These resources are used to set up the environment for the required CLI tools.
  • [COMMAND_EXECUTION]: The documentation includes examples of using the belt CLI to invoke various AI models for video, audio, and caption generation. These commands are limited to the authorized belt tool scope and are consistent with the skill's stated functionality.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided prompts for video creation. While this is an input surface for external data, the use of structured JSON objects for these inputs provides clear boundaries between data and executable instructions, minimizing the risk of accidental obedience to embedded commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:20 PM
Security Audit — agent-trust-hub — video-ad-specs